Run 4. Outer Step 4. Inner Step 19.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486951,
-    5486953,
-    5486955,
-    5486956,
-    5486958,
-    5486960,
-    5486963,
-    5486966
+    5486969,
+    5486972,
+    5486975,
+    5486977,
+    5486979
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c479a54a6f685e62fc87fac36812f0c015c0541294d983f8dc11958bad41591e
+oid sha256:281e23e4f283491a6a6dfab0b6a6b27a846841c30dae69434c93418581e9835d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c079c25392898875c9454cc49c27eaa7445b8a78ce7f2d6f3763d22cd67b8b
+oid sha256:7ce65456d9ce61d89c0230f1c87a5f9cf07eeb4f24131424f28046c67b7c9597
 size 4040701744